© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 49152
    9. 8-RES_FS49152-JB
    11. 26720
    Prev
    Next
    INDEX
    Explanations

    medical terms related to congenital conditions and defects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    746
    +0.13
    0.6%
    161
    +0.10
    0.5%
    52
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    343
    +0.13
    0.01
    118
    +0.10
    0.01
    288
    +0.10
    0.01
    Negative Logits
    ONEY
    -0.70
    Dispatch
    -0.70
     Mile
    -0.69
    FUL
    -0.68
    fulness
    -0.67
    OPS
    -0.67
    bane
    -0.66
    FTWARE
    -0.66
    uyomi
    -0.66
    punk
    -0.65
    POSITIVE LOGITS
    ital
    1.05
    etric
    1.03
    etrical
    0.97
    ities
    0.92
    ially
    0.86
    atal
    0.86
    etr
    0.86
    etermin
    0.82
    ial
    0.81
    obal
    0.81
    Activations Density 0.006%

    No Known Activations